The Journal of the Convergence on Culture Technology (문화기술의 융합)

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

Grade Analysis and Two-Stage Evaluation of Beef Carcass Image Using Deep Learning

딥러닝을 이용한 소도체 영상의 등급 분석 및 단계별 평가

  • 김경남 (부산대학교 IT응용공학과) ;
  • 김선종 (부산대학교 IT응용공학과)
  • Received : 2022.02.28
  • Accepted : 2022.03.08
  • Published : 2022.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Quality evaluation of beef carcasses is an important issue in the livestock industry. Recently, through the AI monitor system based on artificial intelligence, the quality manager can receive help in making accurate decisions based on the analysis of beef carcass images or result information. This artificial intelligence dataset is an important factor in judging performance. Existing datasets may have different surface orientation or resolution. In this paper, we proposed a two-stage classification model that can efficiently manage the grades of beef carcass image using deep learning. And to overcome the problem of the various conditions of the image, a new dataset of 1,300 images was constructed. The recognition rate of deep network for 5-grade classification using the new dataset was 72.5%. Two-stage evaluation is a method to increase reliability by taking advantage of the large difference between grades 1++, 1+, and grades 1 and 2 and 3. With two experiments using the proposed two stage model, the recognition rates of 73.7% and 77.2% were obtained. As this, The proposed method will be an efficient method if we have a dataset with 100% recognition rate in the first stage.

소도체의 품질평가는 축산업 분야의 중요한 문제이다. 최근 인공지능을 기반으로 한 AI 모니터 시스템을 통해 품질 관리사는 소도체 영상의 분석이나 결과 정보를 기반으로 정확한 판단에 도움을 받을 수 있다. 이러한 인공지능의 데이터셋은 성능을 판단하는 중요한 요소이다. 기존의 데이터셋은 표면의 방향이나 해상도가 달라질 수 있다. 본 논문에서는 딥러닝을 이용한 소도축 영상의 등급을 효율적으로 관리할 수 있는 단계별 분류 모델을 제안하였다. 그리고 기존의 세그멘테이션 추출된 영상의 데이터셋의 다양한 조건의 일관성을 위해 새로운 데이터셋 1,300장을 구성하였다. 새로운 데이셋을 이용한 5등급 분류에 대한 딥러닝의 인식률은 72.5%를 얻었다. 제안된 단계별 분류는 1++, 1+, 1등급과 2, 3등급의 차이가 크다는 것을 이용한 방안이다. 이로 인해 제안된 2단계 모델의 두 가지 방법에 따른 실험 결과, 73.7%, 77.2%의 인식률을 얻을 수 있었다. 이처럼 1단계 인식률을 100%를 갖는 데이터셋을 가진다면 더욱 효율적인 방법이 될 것이다.

Keywords

Acknowledgement

이 논문은 2018년도 정부(교육부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초 연구사업임(No. 2018R1D1A1B07045565).

References

  1. V. Wiley and T. Lucas, "Computer vision and image processing: A paper review", International Journal of Artificial Intelligence Research, Vol. 2, No. 1, pp. 28-36, June 2018. https://doi.org/10.29099/ijair.v2i1.42
  2. Soyoung Chung and Min Gyo Chung, "GAN-based Image-to-image Translation using Multi-scale Images", The Journal of the Convergence on Culture Technology, Vol. 6, No. 4, pp. 767-776, 2020. https://doi.org/10.17703/JCCT.2020.6.4.767
  3. Mun-Yong Park, Suk-Ki Lee, Dong-Jin Shin, "A Vehicle Recognition Method based on Radar and Camera Fusion in an Autonomous Driving Environment", International Journal of Advanced Smart Convergence Vol.10 No.4, 263-272, 2021. https://doi.org/10.7236/IJASC.2021.10.4.263
  4. ByungJoo Kim, "Image Enhanced Machine Vision System for Smart Factory", International Journal of Internet, Broadcasting and Communication Vol.13 No.2, pp. 7-13, 2021. https://doi.org/10.7236/IJIBC.2021.13.2.7
  5. Jiyoo Lee, Seung-Jung Shin, "A Study of Video-Based Abnormal Behavior Recognition Model Using Deep Learning", International Journal of Advanced Smart Convergence Vol.9 No.4, pp. 115-119, 2020. https://doi.org/10.7236/IJASC.2020.9.4.115
  6. KyungNamChoi, "Implementation of the stone classification with AI algorithm based on Vggnet neural networks", Smart Media Journal, Vol. 10, No. 1, pp, 32-38, 2021. https://doi.org/10.30693/SMJ.2021.10.1.32
  7. Kyung Ran Oh, Kim, Jeong Hwan, "Technolo gy trends in digital intermediate process using artificial intelligence based on deep learning-Focused on Colourlab Ai software", Journal of Image and Cultural Contents, Vol. 23, pp. 143-174, 2021. https://doi.org/10.24174/jicc.2021.06.23.143
  8. NaeJoung Kwak, DongJu Kim, "Object detection technology trend and development direction using deep learning", International Journal of Advanced Culture Technology Vol.8 No.4, pp. 119-128, 2020. https://doi.org/10.17703/IJACT.2020.8.4.119
  9. Heil Kim, Yeongjee Chung, "Effect of Input Data Video Interval and Input Data Image Similarity on Learning Accuracy in 3D-CNN", International Journal of Internet, Broadcasting and Communication Vol.13 No.2, pp. 208-217, 2021. https://doi.org/10.7236/IJIBC.2021.13.2.208
  10. Soo-Kyoung Park, Na Hojun, and Ji-Hye Kim, "A Study on Basalization of the Classification in Mountain Ginseng and Plain Ginseng Images in Artificial Intelligence Technology for the Detection of Illegal Mountain Ginseng", The Journal of Bigdata, Vol. 5, No. 1, pp. 209-225, Aug. 2020. https://doi.org/10.36498/kbigdt.2020.5.1.209
  11. V. Meshram, K. Patil, V. Meshram, D. Hanchate, and S.D. Ramkteke, "Machine learning in agriculture domain: A state-of-art survey", Artificial Intelligence in the Life Sciences, Vol. 1, 2021. https://doi.org/10.1016/j.ailsci.2021.100010.
  12. Xing S, Lee M, and Lee K. "Citrus pests and diseases recognition model using weakly dense connected convolution network". Sensors, Vol. 19, No. 14, 2019. https://doi.org/10.3390/s19143195
  13. Seon-Jong Kim, "Image analysis and dimension reduction for color-texture space using IOCLBP", Journal of Korean Institute of Information Technology, Vol. 19, No. 9, pp. 87-93, Sept. 2021. https://doi.org/10.14801/jkiit.2021.19.9.87
  14. Hossain MS, Al-Hammadi M, Muhammad G. "Automatic fruit classification using deep learning for industrial applications". IEEE Trans Ind Inf, Vol. 15, No. 2, 2019. https://doi.org/10.1109/TII.2018.2875149
  15. Gwan-Tae Kim, "Beef carcass rating standard supplement(Draft) development status", Korean Society for Food Science of Animal Resources, Vol. 5, No.2, pp. 85-92, 2016.
  16. AI dataset, www.aihub.or.kr
  17. Hunsoo Kim et al, "Development of a deep learning model for the quality grade assessment of livestock product : Focusing on cattle images", The Conferences of Korean Institute Of Industrial Engineers, pp. 1955-1981, June 2021.
  18. H.-C. Yoo, J.-G. Lim, A.-Y. Lee, B.-G. Kim, Y.-W. Seo, and S.-M. Kim, "Development of an image acquisition device based on smartphone for grading determination of beef carcass", Journal of the Korea Academia-Industrial cooperation Society, Vol. 22, No. 11, pp. 839-847, 2021. https://doi.org/10.5762/KAIS.2021.22.11.839